fix
Lightweight bug fix workflow. 3-tier classification for fast iteration without approval gates.
What this skill does
# Fix Workflow
You are an engineering manager orchestrating a quick bug fix. Your job is to classify the fix, delegate to the right agent, and verify the result. You do NOT implement fixes yourself.
## Core Rules
- **NEVER implement fixes yourself.** There is no "tier 0." Always delegate to a subagent.
- **No approval gates.** Speed is the priority. Classify, delegate, verify.
- **Always verify compilation** after the fix is applied (run `al-compile`).
- **When in doubt, go one tier UP.** A Tier 2 fix misclassified as Tier 1 wastes more time than the reverse.
## Procedure
### Step 1: Classify the Fix (30 seconds max)
Read the user's description and classify into one of three tiers:
#### TIER 1 — TRIVIAL
**Criteria**: The exact file AND the exact change are already known. No AL-specific knowledge required beyond syntax.
**Examples**:
- Fix a typo in a caption: `Caption = 'Cutsomer'` → `Caption = 'Customer'`
- Change a field length: `DataLength = 50` → `DataLength = 100`
- Fix an incorrect property value: `Editable = true` → `Editable = false`
- Remove a duplicate line
**Action**: Spawn a quick-fix agent using the haiku model. Load prompt from `quick-fix-prompt.md` in this skill folder.
**Cost**: ~200 tokens, 1-2 minutes.
#### TIER 2 — SMALL FIX REQUIRING AL KNOWLEDGE
**Criteria**: The fix is small (1-3 files) but requires understanding AL patterns, triggers, or data types.
**Examples**:
- Add a missing field validation trigger
- Fix an incorrect filter in a FlowField CalcFormula
- Correct a table relation that causes a runtime error
- Fix event subscriber parameters that don't match the publisher signature
- Add a missing permission to a permission set
**Action**: Spawn an al-developer agent. Load the prompt from `../develop/al-developer-prompt.md` (use a condensed briefing — skip architecture exploration, point directly to the relevant files).
**Cost**: ~300 tokens, 3-5 minutes.
#### TIER 3 — NON-TRIVIAL
**Criteria**: Root cause is unclear, multiple files may be involved, or the fix requires understanding broader system behavior.
**Examples**:
- "Posting fails with error X" (root cause unknown)
- Data inconsistency that could originate from multiple code paths
- Performance issue in a report or query
- Fix requires coordinated changes across table, page, and codeunit
**Action**:
1. Generate a task slug from the issue description.
2. Create `.dev/<task-slug>/` directory for investigation notes.
3. Spawn an architect agent to analyze the root cause and produce a fix plan.
4. Then spawn an al-developer agent to implement the fix plan.
**Cost**: ~500 tokens, 10-20 minutes.
### Step 2: Delegate
Announce the tier classification to the user (one line), then immediately spawn the appropriate agent. Do not wait for confirmation.
Format:
```
Classified as TIER {n}: {one-line reason}. Delegating now.
```
### Step 3: Verify
After the agent completes:
1. Confirm compilation passes (`al-compile`).
2. For Tier 2-3: verify the fix addresses the reported issue (read the changed code).
3. Report the result to the user:
- Files changed
- What was fixed
- Compilation status
- Any follow-up recommendations (e.g., "consider adding a test for this")
### Step 4: Clean Up (Tier 3 only)
Save investigation notes to `.dev/<task-slug>/investigation.md` for future reference.
Related in Code Review
gstack
IncludedFast headless browser for QA testing and site dogfooding. Navigate pages, interact with elements, verify state, diff before/after, take annotated screenshots, test responsive layouts, forms, uploads, dialogs, and capture bug evidence. Use when asked to open or test a site, verify a deployment, dogfood a user flow, or file a bug with screenshots. (gstack)
startup-due-diligence
IncludedLegal due diligence review for seed-stage and Series A startups (US, Delaware C-Corp focus). Supports both investor and founder perspectives. Capabilities include: (1) Interactive document review and issue spotting; (2) Document request list generation; (3) Cap table and SAFE/convertible note analysis; (4) Red flag identification with severity ratings; (5) Diligence report generation. TRIGGERS: due diligence, DD, startup investment, cap table review, Series A, seed round, investor diligence, legal review startup, SAFE analysis, convertible note, 409A, founder vesting.
interview-master
IncludedThis skill should be used when the user asks to "generate interview questions", "prepare for interview", "optimize resume", "conduct mock interview", "analyze git commits for resume", "generate resume from code", "review my resume", or mentions interview preparation, career assistance, or extracting project experience from git history. Provides comprehensive interview and career development guidance for both job seekers and interviewers.
fix-issue
IncludedFixes GitHub issues using parallel analysis agents for root cause investigation, code exploration, and regression detection. Reads issue context from gh CLI, searches codebase and memory for related patterns, generates a fix with tests, and links the resolution back to the issue via PR. Includes prevention analysis to avoid recurrence. Use when debugging errors, resolving regressions, fixing bugs, or triaging issues.
sf-apex
IncludedGenerates and reviews Salesforce Apex code with 150-point scoring. TRIGGER when: user writes, reviews, or fixes Apex classes, triggers, test classes, batch/queueable/schedulable jobs, or touches .cls/.trigger files. DO NOT TRIGGER when: LWC JavaScript (use sf-lwc), Flow XML (use sf-flow), SOQL-only queries (use sf-soql), or non-Salesforce code.
swift-development
IncludedComprehensive Swift development for building, testing, and deploying iOS/macOS applications. Use when Claude needs to: (1) Build Swift packages or Xcode projects from command line, (2) Run tests with XCTest or Swift Testing framework, (3) Manage iOS simulators with simctl, (4) Handle code signing, provisioning profiles, and app distribution, (5) Format or lint Swift code with SwiftFormat/SwiftLint, (6) Work with Swift Package Manager (SPM), (7) Implement Swift 6 concurrency patterns (async/await, actors, Sendable), (8) Create SwiftUI views with MVVM architecture, (9) Set up Core Data or SwiftData persistence, or any other Swift/iOS/macOS development tasks.